MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Paste a developer error, get the real cause and the fix. Offline, zero-dependency explainers for CORS, ESM/CJS, npm ERESOLVE, ChunkLoadError, Postgres/Supabase DATABASE_URL and Next.js build errors.
npm MIT -
dataxplan-mcpgithub.com/arikanatakan/dataxplan-mcpupdated this year
Read PostgreSQL EXPLAIN plans for AI agents: bottlenecks, estimation errors, fixes, charts.
pypi MIT ★ 2 -
Your Terraform plan, explained — plan explainer, drift narrator, and error decoder. Local-first, BYO-LLM (Anthropic/OpenAI/Ollama), MCP-native.
Apache-2.0 -
Validate EU e-invoices (Peppol, XRechnung, Factur-X, UBL, CII) and explain error codes.
npm -
Run DevTools API Studio collections (and Postman collections) from a terminal or CI, with JUnit reports; explain build logs with your team's Error Memory; check Code Flow Maps and serve them to coding agents over MCP.
npm -
Agentic-BIM-Compliancegithub.com/Prajwalkadam29/Agentic-BIM-Complianceupdated this year
This project replaces error-prone, 2-day manual structural reviews with a 4-minute Agentic AI workflow that parses IFC models for code compliance. It ensures structural safety through real-time 3D visual overlays, explainable reports, and automated "auto-fix" design suggestions.
MIT ★ 1 -
MCP server for Kaspa (Toccata) script tooling: disassemble scripts, estimate compute cost, and explain txscript errors. Pure TS, generated from rusty-kaspa v2.1.0.
npm MIT -
Checks DHL API requests before you send them and explains DHL's errors, with sources. React, NestJS, MCP server. Not affiliated with DHL.
MIT -
@daraja-mcp/supportgithub.com/safaricom/daraja-pocupdated this year
The 24/7 M-Pesa Support Assistant — MCP server for Daraja developers. Diagnose any error, explain any concept, validate any integration, verify fixes against sandbox. Read-only knowledge tools + sandbox-only verification.
npm MIT -
turboc-mcp-servergithub.com/BBSRGUY/turboc-mcp-serverupdated this year
🕹️ Give your AI a real 1992 Borland Turbo C 3.0 compiler — an MCP server with 12 tools: compile, run, lint, benchmark, disassemble & explain errors on genuine 16-bit DOS.
MIT ★ 1 -
Earth Agent is a Cursor-like AI agent for Google Earth Engine. It can be used right in your browser as a Chrome extension or through MCP server support. It helps you do anything related to Google Earth Engine automatically through chatting (write code, run analysis, debug errors, explain maps, and manage your environment). Hatched from sundai.club.
MIT ★ 105 -
The ediFabric MCP server lets AI assistants validate X12 and HIPAA EDI files up to SNIP level 4 and explain each error, convert EDI to JSON and back, generate 999 and 997 acknowledgments, split files into transactions, and describe any transaction's structure. It runs ediFabric Native locally; your EDI files stay on your machine.
npm NOASSERTION ★ 1 -
YouTube Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_trainability`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
An MCP server for data validation, structuring, visualization, and SQLAlchemy-based db creation out of raw .html, backed by schema.org, pydantic, at matplotlib
MIT